LLMs tell bad jokes because they avoid surprises • Hacker News Board

Re: LLMs tell bad jokes because they avoid surprises

#161

Post by IT4MD » Tue, Aug 19, 2025, 4:28 PM UTC

brookst wrote: post #60

ozgung wrote: post #57

Earlier quoted context omitted.

"Why did the sun climb a tree?" Claude Opus 4.1: - To get to a higher branch of astronomy - Because it wanted to reach new heights - To see the dawn of a new day from a better view ChatGPT 5 Thinking: After thinking for 26 seconds: - To check on its solar panels—the leaves.

With more thorough prompting: > Complete the following joke. Think carefully and make it really funny! Think like a great comedian and find that perfect balance of simple, short, surprising, relevant, but most of all funny. Don’t use punchlines that are irrelevant, non sequiturs, or which could be applied to any other setup. Make something funny just for this one setup! Here goes: Why did the sun climb a tree? Claude…

"To demand photon credit from the leaves" is funny.

Re: LLMs tell bad jokes because they avoid surprises

#162

Post by phorkyas82 » Wed, Aug 20, 2025, 3:25 AM UTC

IshKebab wrote: post #11

This sounds really convincing but I'm not sure it's actually correct. The author is conflating the surprise of punchlines with their likelihood. To put it another way, ask a professional comedian to complete a joke with a punchline. It's very likely that they'll give you a funny surprising answer. I think the real explanation is that good jokes are actually extremely difficult. I have young children (4 and 6). Even 6…

Some human attempts: "Why did the sun climb a tree?" "Because it was chased by the Great Bear."

"Why did The Sun climb a tree?" "To spy on The Royal Family having picnic."

Re: LLMs tell bad jokes because they avoid surprises

#163

Post by wrp » Wed, Aug 20, 2025, 9:43 AM UTC

dfabulich wrote: post #156

ajuc wrote: post #148

So there's 2 thesis in this article. 1. joke quality is how much sense the punchline makes as a completion of the setup minus the probability of finding the punchline given just the setup 2. jokes are subjective, people disagree wildly about how good a joke is, so if you aggregate preferences you get mediocre jokes at best. I think 1 is the important part. If it was just 2 - comedians with widespread appeal wouldn't…

Author here. I think the term "widespread appeal" may be misleading. There are comedians who can attract a very large audience, large enough to make them major celebrities, but that doesn't mean that aggregating preferences doesn't produce mediocre jokes. Instead, comedians build an audience of like-minded people, and get to know that audience very well. It's a little bit like the process of finding product-market fi…

I mainly agree with your argument, but I think "inevitable in hindsight" needs reconsideration. Following the incongruity model, humor comes when the punchline forces a change in perspective on the setup. So it is not that the new perspective is inevitable, but that it was such a less likely interpretation of the setup that it didn't occur to the audience.

Considered this way, the question is whether an LLM could be trained to create joke setups that are ambiguous in the right way, with one obvious interpretation and a hidden but possible interpretation that will be forced by the punchline.